LGMLApr 27

Stochastic simultaneous optimistic optimization

arXiv:2604.2453736.9111 citations
AI Analysis

For bandit optimization in general spaces, this removes the need for prior knowledge of the semi-metric, making the algorithm more practical.

StoSOO solves global maximization of a noisy function without requiring knowledge of its local smoothness, achieving performance nearly matching algorithms that are specifically tuned for the smoothness parameters.

We study the problem of global maximization of a function f given a finite number of evaluations perturbed by noise. We consider a very weak assumption on the function, namely that it is locally smooth (in some precise sense) with respect to some semi-metric, around one of its global maxima. Compared to previous works on bandits in general spaces (Kleinberg et al., 2008; Bubeck et al., 2011a) our algorithm does not require the knowledge of this semi-metric. Our algorithm, StoSOO, follows an optimistic strategy to iteratively construct upper confidence bounds over the hierarchical partitions of the function domain to decide which point to sample next. A finite-time analysis of StoSOO shows that it performs almost as well as the best specifically-tuned algorithms even though the local smoothness of the function is not known.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes